© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 54974
    Prev
    Next
    INDEX
    Explanations

    punctuations, especially periods and colons, indicating the structure of complex technical descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paz
    -0.07
    PLY
    -0.07
    mah
    -0.06
    abaj
    -0.06
    adies
    -0.06
    forman
    -0.06
    cott
    -0.06
    adium
    -0.06
     Programm
    -0.06
    ÅĻeh
    -0.06
    POSITIVE LOGITS
    Ø´ÙĪ
    0.07
    hest
    0.06
    obby
    0.06
    REFERRED
    0.06
    _SR
    0.06
    æ³³
    0.06
    ilo
    0.06
     Cord
    0.06
     ass
    0.05
    ìĥ¤
    0.05
    Activations Density 0.013%

    No Known Activations